Glean 拾遗
Daily /2026-11-18 / When Claude writes 90% of the code, verification becomes the system

When Claude writes 90% of the code, verification becomes the system

Source x.com Glean’d 2026-11-18 12:55 Read 1 min
AI summary

Claude Code's team now has Claude write and review roughly 90% of its code. Addy Osmani's new post covers how the verification layer has to be built at that ratio, so the agent can show evidence that a change is actually correct. Two practices stand out. First, the review rules in REVIEW.md are always read from the main branch, never from the PR under review, and new submission gates run in observe mode long enough to measure false blocks before being enforced. Second, a 39-item reliability checklist where each item states how to spot it in a diff and which real incident produced it; Claude runs only the 3-10 items a given diff triggers. Useful for engineers building coding agents, CI gates, and automated code review.

Original · 1 min
x.com ↗
§ 1

The Claude Code team has Claude write — and review — roughly 90% of its code. Addy Osmani's new post is about how, at that ratio, they get the agent to produce evidence that it actually fixed what it was supposed to fix.

Two of their practices strike me as the most worth copying.

Claude Code 团队约 90% 的代码由 Claude 来写、来审。Addy Osmani 这篇新文章讲的是,到了这个比例,他们怎么让 Agent 拿出证据证明自己改对了。

我觉得最值得抄的有两个做法。

§ 2

One: the change can never touch the rules that judge it. Code Review always pulls REVIEW.md from the main branch and never reads the copy inside the PR. New commit gates also start out in observe mode for a while, so the false blocks become visible before anything is enforced.

一:是改动碰不到判它的规则。Code Review 读的 REVIEW.md 永远取自主分支,不读 PR 里的版本。新的提交门禁也会先开 observe 模式跑一段,把误拦看清楚了再强制执行。

§ 3

Two: a 39-item reliability checklist, where each entry spells out how to spot the problem in a diff and which incident it came from. After reading the diff, Claude only checks the 3 to 10 items that were actually triggered — nobody has to memorize the incident history.

二:是一份 39 条的可靠性清单,每条都写明从 diff 里怎么识别、背后是哪次事故。Claude 读完 diff 只查触发到的那 3~10 条,谁都不用把历史事故背下来。

§ 4

Running many Claudes at once only works if the verification layer underneath is reliable enough. This post treats that layer as a proper system, which makes it worth a close read for anyone building agent systems.

Original: https://claude.dev/blog/how-the-claude-code-team-thinks-about-verification/

想同时跑很多个 Claude,前提是验证这一层足够可靠。这篇把这层当成正经系统来做,挺值得做 Agent 工程的朋友细读。

原文:https://claude.dev/blog/how-the-claude-code-team-thinks-about-verification/

Open source ↗